检索结果-内蒙古大学图书馆

5th International Conference on Neural Networks and Neurotechnologies, NeuroNT 2024

作者： Kupriyanov, Mikhail S. Shichkina, Yulia A. Ilin, Semyon E. Saint Petersburg Electrotechnical University 'LETI' Department of Computer Science and Engineering St. Petersburg Russia

ISBN: (纸本)9798350363739

The article aims to discuss the peculiarities of using the Machine Learning Operations paradigm in the context of addressing the task of temporal action detection in video data. The results of applying Machine Learning Operations to the aforementioned task are analyzed at three levels of machine learning workflow, namely, at the level of machine learning system design, at the level of machine learning system components, and at the level of elements within the machine learning system components. It is emphasized that Machine Learning Operations facilitates the procedures of designing, developing and deploying the temporal action detection workflow. © 2024 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Analysis of Approaches for Identifying Key Skills in Vacancies 27

Analysis of Approaches for Identifying Key Skills in Vacanci...

引用

27th International Conference on Soft Computing and Measurements, SCM 2024

作者： Korytov, Pavel V. Kholod, Ivan I. Gribetskiy, Yan Yu. Andreeva, Ekaterina A. Saint Petersburg Electrotechnical University 'LETI' Faculty of Computer Science and Technology Department of Computer Science and Engineering Saint-Petersburg Russia Saint Petersburg Electrotechnical University 'LETI' Faculty of Computer Science and Technology Department of Information Systems Saint-Petersburg Russia

ISBN: (纸本)9798350363708

The task of identifying key skills from job vacancies descriptions is considered in the article. The source data consists of vacancy texts from the 'Jobs in Russia' portal, in which skill-related entities were manually annotated. Keyword extraction methods (YAKE, PositionRank and WikiNEuRal, KBIR-InSpec), and a named entity recognition model trained on the source data are compared. © 2024 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Application of Neural Network Keyword Extraction Methods for Student's CV Compilation from Discipline Work Programs 26

Application of Neural Network Keyword Extraction Methods for...

引用

26th International Conference on Soft Computing and Measurements, SCM 2023

作者： Kholod, Ivan I. Korytov, Pavel V. Sorochina, Maria V. Saint-Petersburg Electrotechnical University LETI Department of Computer Science and Engineering Saint-Petersburg Russia Saint-Petersburg Electrotechnical University LETI Department of Software Engineering and Computer Applications Saint-Petersburg Russia

ISBN: (纸本)9798350322484

The paper considers application of natural language processing methods (NLP) to solve the task of identifying the core skills acquired by students in the process of education. An ensemble solution, consisting of models WikiNEuRAL, KBIR-Inspec, ruGTP3Large, word2vec, and other NLP methods, is used to extract and process Russian language keywords. The described method was developed to automate the compilation of a student's CV in the information system called 'Partner's Account' of the LETI' university. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Human-Machine Interaction in E-commerce: a Multi-Faceted Examination of CAPTCHA Effect

Human-Machine Interaction in E-commerce: a Multi-Faceted Exa...

引用

2024 Conference of Young Researchers in Electrical and Electronic engineering, ElCon 2024

作者： Okoli, Kingsley Joseph, Innocent Chijioke, Famous Bekeneva, Yana Chijioke, Amadi Kodondo, Ibrahim Saint Petersburg Electrotechnical University 'LETI' Department of Computer Science and Engineering Saint Petersburg Russia Saint Petersburg Electrotechnical University 'LETI' Department of Control in Technical Systems Saint Petersburg Russia Saint Petersburg Electrotechnical University 'LETI' Department of Information Systems and Technologies Saint Petersburg Russia

ISBN: (纸本)9798350360646

The growing prevalence of automated threats in e-commerce necessitates effective security measures, exemplified by CAPTCHAs (Completely Automated Public Turing test to tell computers and Humans Apart). However, the use of CAPTCHAs introduces challenges related to user perception, engagement, and frustration. This study aims to comprehensively analyze the impact of CAPTCHAs on ecommerce transactions, including their influence on user behavior, security effectiveness, and the complexity of their implementation. Through a structured questionnaire-based approach, we gathered insights from users, assessing their experiences and perceptions of CAPTCHAs during online shopping. Our analysis involved quantitative data, utilizing statistical software, to provide a holistic understanding of these security measures in the e-commerce domain. Users support the effort to make CAPTCHAs engaging, and many find gamified elements positive. A substantial number express high frustration with multiple CAPTCHAs, affecting their willingness to return to e-commerce platforms. This study outlines the importance of optimizing CAPTCHAs to balance security and user experience in e-commerce. © 2024 IEEE.

关键词： CAPTCHA E-commerce Gamified Security User-Centric

来源：评论

学校读者我要写书评

暂无评论

The Possibility of Applying the Theory of Multioperations to Build Self-learning Artificial Intelligence Systems with the Explainability Property 4

The Possibility of Applying the Theory of Multioperations to...

引用

4th International Conference on Neural Networks and Neurotechnologies, NeuroNT 2023

作者： Todikov, Sergey I. Saint Petersburg Electrotechnical University 'Leti' Department of Computer Science and Engineering Saint Petersburg Russia

ISBN: (纸本)9798350301526

When developing artificial intelligence systems, one of the important aspects is a more accurate description of the considered events and their uncertainties. At the moment, most of the modern solution's mathematical apparatus have a significant drawback-The data is considered only between two logical elements-True and false. In this regard, it is impossible to give detailed description of the considered events and their uncertainties. Another important aspect of Artificial Intelligence systems is the explainability property, since making key decisions, it is necessary to explain of how the AI system came to its answer. One of the possible solutions is to apply the theory of multioperations. The paper suggests a methodology for building self-learning systems of explainable artificial intelligence based on the theory of multioperations and presents an abstract example of the application of the developed methodology for building an AI system of a medical field of study. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

ETDA a tool for the development of e-Tongues

ETDA a tool for the development of e-Tongues

引用

2023 International Young Engineers Forum in Electrical and computer engineering, YEF-ECE 2023

作者： Reis, Tiago Fino, M. Helena Raposo, Maria Nova School of Science and Technology Department of Electrotechnical and Computer Engineering Caparica Portugal Department of Physics Caparica Portugal

ISBN: (纸本)9798350300420

This paper presents the Electronic Tongues Data Analytics (ETDA) tool for automatically extracting the relevant features from data obtained from an electronic tongue (e-Tongue) system based on impedance spectroscopy measurements. The tool was implemented in Python and was created to assist with the development of e-Tongues. This tool helps to quickly visualize the data from the experiments and can automatically create and calibrate the Principal Components Analysis (PCA) to fit the concentrations of a determined molecule present in the complex media. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Completion Method Based on Using Multi-Hop Reasoning 10

Knowledge Graph Completion Method Based on Using Multi-Hop R...

引用

10th International Conference on Information Technology and Nanotechnology, ITNT 2024

作者： Golovin, Aleksei Zhukova, Nataly Kulikov, Igor Saint Petersburg Electrotechnical University 'LETI' Department Of Software Engineering And Computer Applications Saint-Petersburg Russia Saint-Petersburg Russia

ISBN: (纸本)9798350372939

In this paper, the method for knowledge graph completion based on using multi-hop reasoning is proposed. The relevance of the problem is due to the widespread use of large sparse knowledge graphs with incomplete data. Within the research, the method for restoring the structure of a knowledge graph using sequence-to-sequence multi-hop reasoning, based on the transformer architecture, is proposed. To evaluate the effectiveness of the proposed method, the study of its properties was carried out and the results were compared with the results of the existing methods used for predicting relations in the knowledge graphs. The proposed solution almost achieves the same results as methods based on embeddings. The evidential paths generated by the proposed method ensure the interpretability of the results. Our method does not rely on existing relations to create an evidential path and has the flexibility to restore missing relations in the path. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Application of Attack Graphs to Simulate the Violation of the Movement of Vehicles in the Convoy 26

Application of Attack Graphs to Simulate the Violation of th...

引用

26th International Conference on Soft Computing and Measurements, SCM 2023

作者： Fatkieva, Rosa R. Saint Petersburg Electrotechnical University LETI Department of Computer Science and Engineering St. Petersburg Russia

ISBN: (纸本)9798350322484

The paper investigates algorithms for the movement of unmanned vehicles. A mathematical model of the functioning of the control system is described. The analysis of information threats during the movement of vehicles in a convoy was carried out. Graphs of information attacks are constructed. On the example of modeling threats to the transmission and processing of information, possible violations of functioning are shown. Measures to neutralize them are proposed. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Long-Short Term Memory decision model for device argumentation in ambient assisted living

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第12期15卷 4073-4083页

作者： Kumar, G. S. Madhan ShivaPrakash, S.P. Krinkin, Kirill Shichkina, Yulia A. Department of Information Science and Engineering JSS Science and Technology University Karnataka Mysore570006 India School of Computer Science and Engineering Constructor University Bremen Germany Department of Technologies of Artificial Intelligence in Physiology and Medicine Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

The global elderly population is on the rise, posing significant challenges in both developed and developing nations. These challenges include issues related to mobility, falls, and the performance of daily tasks. However, the demands of today’s fast-paced lifestyles make it difficult to provide constant care for the elderly, driving them towards a preference for independent living. To address this need for independent living, the concept of Ambient assisted living (AAL) has been developed. AAL is an intelligent system that employs sensors and devices to monitor and assist elderly individuals in their daily activities. Nevertheless, conflicts can arise when multiple sensors report conflicting activities concurrently, leading to device argumentation. To tackle this issue, this paper introduces a novel Long Short-Term Memory (LSTM)-based learning technique for aiding decision-making during device argumentation concerning activity occurrences. The LSTM model classifies user activities and sensor status values, employing an innovative approach to identify device argumentation within these classified activities. This LSTM decision-making (LDM) model effectively resolves device argumentation and accurately identifies the target activity. An experiment using a combined dataset from the ARAS and CASE datasets demonstrates the superiority of the proposed model, achieving an accuracy of 90.30%, precision of 85.66%, recall of 95.23%, and an F1-Score of 90.22%. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Combination of Soft Attention-aided CNN Models using Dempster-Shafer Theory for Skin Cancer Classification

A Combination of Soft Attention-aided CNN Models using Demp...

引用

International Conference on Current Problems of Applied Mathematics and computer Systems, CPAMCS 2023

作者： Sarkar, Sujan Ray, Amartya Kaplun, Dmitrii Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9783031640094

Skin cancer is one of the most deadly forms of cancer in the world, causing hundreds of deaths every year. Researchers have been developing various computer-aided diagnosis (CAD) systems to help medical professionals classify the types of skin cancer using different image modalities. In this paper, we propose a model, which combines the outcomes of three separately trained attention-based convolutional neural networks (CNNs) using the Dempster-Shafer theory. The three base learners used in this paper are ResNet50, InceptionResNetV2 and Dense-Net201, each of which is aided by a soft attention module. For evaluating the proposed model, we have considered a publicly accessible skin cancer dataset, called HAM10000. This is a challenging dataset to work with as it is a class imbalanced dataset. Our proposed approach yields an accuracy of 0.932, which is better than many recently published methods found in the literature. The source code is available at: https://***/Cmatermedicalimageanalysis/DST_Combination © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：